intel-extension-for-pytorch: IPEX 2.1.10+xpu regression with Stable Diffusion workloads that were working with IPEX 2.0.120+xpu on WSL2/Linux

Describe the bug

Running ComfyUI, a Stable Diffusion frontend, with my Docker image here, I am getting issues with the simplest default workflow which uses Stable Diffusion 1.5. I am getting the following even after disabling ipex.optimize().

2023-12-14 08:57:22,727 - root - ERROR - !!! Exception during processing !!!
2023-12-14 08:57:22,727 - root - ERROR - Traceback (most recent call last):
  File "/ComfyUI/execution.py", line 153, in recursive_execute
    output_data, output_ui = get_output_data(obj, input_data_all)
  File "/ComfyUI/execution.py", line 83, in get_output_data
    return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
  File "/ComfyUI/execution.py", line 76, in map_node_over_list
    results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
  File "/ComfyUI/nodes.py", line 1299, in sample
    return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
  File "/ComfyUI/nodes.py", line 1269, in common_ksampler
    samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
  File "/ComfyUI/comfy/sample.py", line 100, in sample
    samples = sampler.sample(noise, positive_copy, negative_copy, cfg=cfg, latent_image=latent_image, start_step=start_step, last_step=last_step, force_full_denoise=force_full_denoise, denoise_mask=noise_mask, sigmas=sigmas, callback=callback, disable_pbar=disable_pbar, seed=seed)
  File "/ComfyUI/comfy/samplers.py", line 715, in sample
    return sample(self.model, noise, positive, negative, cfg, self.device, sampler, sigmas, self.model_options, latent_image=latent_image, denoise_mask=denoise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed)
  File "/ComfyUI/comfy/samplers.py", line 621, in sample
    samples = sampler.sample(model_wrap, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
  File "/ComfyUI/comfy/samplers.py", line 560, in sample
    samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
  File "/deps_latest/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/ComfyUI/comfy/k_diffusion/sampling.py", line 137, in sample_euler
    denoised = model(x, sigma_hat * s_in, **extra_args)
  File "/deps_latest/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/deps_latest/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/ComfyUI/comfy/samplers.py", line 284, in forward
    out = self.inner_model(x, sigma, cond=cond, uncond=uncond, cond_scale=cond_scale, model_options=model_options, seed=seed)
  File "/deps_latest/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/deps_latest/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/ComfyUI/comfy/samplers.py", line 274, in forward
    return self.apply_model(*args, **kwargs)
  File "/ComfyUI/comfy/samplers.py", line 271, in apply_model
    out = sampling_function(self.inner_model, x, timestep, uncond, cond, cond_scale, model_options=model_options, seed=seed)
  File "/ComfyUI/comfy/samplers.py", line 252, in sampling_function
    cond_pred, uncond_pred = calc_cond_uncond_batch(model, cond, uncond_, x, timestep, model_options)
  File "/ComfyUI/comfy/samplers.py", line 226, in calc_cond_uncond_batch
    output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks)
  File "/ComfyUI/comfy/model_base.py", line 85, in apply_model
    model_output = self.diffusion_model(xc, t, context=context, control=control, transformer_options=transformer_options, **extra_conds).float()
  File "/deps_latest/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/deps_latest/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/ComfyUI/comfy/ldm/modules/diffusionmodules/openaimodel.py", line 854, in forward
    h = forward_timestep_embed(module, h, emb, context, transformer_options, time_context=time_context, num_video_frames=num_video_frames, image_only_indicator=image_only_indicator)
  File "/ComfyUI/comfy/ldm/modules/diffusionmodules/openaimodel.py", line 46, in forward_timestep_embed
    x = layer(x, context, transformer_options)
  File "/deps_latest/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/deps_latest/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/ComfyUI/comfy/ldm/modules/attention.py", line 606, in forward
    x = block(x, context=context[i], transformer_options=transformer_options)
  File "/deps_latest/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/deps_latest/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/ComfyUI/comfy/ldm/modules/attention.py", line 433, in forward
    return checkpoint(self._forward, (x, context, transformer_options), self.parameters(), self.checkpoint)
  File "/ComfyUI/comfy/ldm/modules/diffusionmodules/util.py", line 189, in checkpoint
    return func(*inputs)
  File "/ComfyUI/comfy/ldm/modules/attention.py", line 493, in _forward
    n = self.attn1(n, context=context_attn1, value=value_attn1)
  File "/deps_latest/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/deps_latest/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/ComfyUI/comfy/ldm/modules/attention.py", line 388, in forward
    return self.to_out(out)
  File "/deps_latest/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/deps_latest/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/deps_latest/venv/lib/python3.10/site-packages/torch/nn/modules/container.py", line 215, in forward
    input = module(input)
  File "/deps_latest/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/deps_latest/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
  File "/deps_latest/venv/lib/python3.10/site-packages/torch/nn/modules/linear.py", line 114, in forward
    return F.linear(input, self.weight, self.bias)
RuntimeError: mat1 and mat2 must have the same dtype, but got Float and Half

Prompt executed in 0.08 seconds

This and other complex processing workloads for most part had no issues with IPEX 2.0.120+xpu. I know also this isn’t a Docker issue either from the image or Docker itself because doing the installation sanity check yields the following.

root@fedora:/ComfyUI# python -c "import torch; import intel_extension_for_pytorch as ipex; print(torch.__version__); print(ipex.__version__); [print(f'[{i}]: {torch.xpu.get_device_properties(i)}') for i in range(torch.xpu.device_count())];"
/usr/local/lib/python3.10/dist-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: ''If you don't plan on using image functionality from `torchvision.io`, you can ignore this warning. Otherwise, there might be something wrong with your environment. Did you have `libjpeg` or `libpng` installed before building `torchvision` from source?
  warn(
2.1.0a0+cxx11.abi
2.1.10+xpu
[0]: _DeviceProperties(name='Intel(R) Arc(TM) A770 Graphics', platform_name='Intel(R) Level-Zero', dev_type='gpu, support_fp64=1, total_memory=16288MB, max_compute_units=512, gpu_eu_count=512)

There are similar but probably different problems with other Stable Diffusion front ends, where I also tested out SD.Next and the dev branch of stable-diffusion-webui to sanity check if it was just a ComfyUI issue and although not in Docker, I got similar issues with similar simple workloads and setup with the latest IPEX on both frontends. SD.Next just says loading IPEX fails and doesn’t do anything while stable-diffusion-webui does have a backtrace but IPEX support is in beta and it has to do with Generators not existing which is a separate issue from this one which I can file if someone requests it.

Versions

Ran inside Ubuntu 22.04 Docker container with aforementioned image with Fedora 39 host

PyTorch version: 2.1.0a0+cxx11.abi PyTorch CXX11 ABI: Yes IPEX version: 2.1.10+xpu IPEX commit: a12f9f650 Build type: Release

OS: Ubuntu 22.04.3 LTS (x86_64) GCC version: N/A Clang version: N/A IGC version: N/A CMake version: N/A Libc version: glibc-2.35

Python version: 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0] (64-bit runtime) Python platform: Linux-6.6.6-200.fc39.x86_64-x86_64-with-glibc2.35 Is XPU available: True DPCPP runtime version: N/A MKL version: N/A GPU models and configuration: [0] _DeviceProperties(name=‘Intel® Arc™ A770 Graphics’, platform_name=‘Intel® Level-Zero’, dev_type='gpu, support_fp64=1, total_memory=16288MB, max_compute_units=512, gpu_eu_count=512) Intel OpenCL ICD version: 23.17.26241.33-647~22.04 Level Zero version: 1.3.26241.33-647~22.04

CPU: Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 48 bits physical, 48 bits virtual Byte Order: Little Endian CPU(s): 32 On-line CPU(s) list: 0-31 Vendor ID: AuthenticAMD Model name: AMD Ryzen 9 5950X 16-Core Processor CPU family: 25 Model: 33 Thread(s) per core: 2 Core(s) per socket: 16 Socket(s): 1 Stepping: 0 Frequency boost: enabled CPU max MHz: 5084.0000 CPU min MHz: 550.0000 BogoMIPS: 6800.05 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk clzero irperf xsaveerptr rdpru wbnoinvd arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca fsrm debug_swap Virtualization: AMD-V L1d cache: 512 KiB (16 instances) L1i cache: 512 KiB (16 instances) L2 cache: 8 MiB (16 instances) L3 cache: 64 MiB (2 instances) NUMA node(s): 1 NUMA node0 CPU(s): 0-31 Vulnerability Gather data sampling: Not affected Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Mmio stale data: Not affected Vulnerability Retbleed: Not affected Vulnerability Spec rstack overflow: Vulnerable: Safe RET, no microcode Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; Retpolines, IBPB conditional, IBRS_FW, STIBP always-on, RSB filling, PBRSB-eIBRS Not affected Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected

Versions of relevant libraries: [pip3] intel-extension-for-pytorch==2.1.10+xpu [pip3] numpy==1.26.2 [pip3] torch==2.1.0a0+cxx11.abi [pip3] torchaudio==2.1.0a0+cxx11.abi [pip3] torchvision==0.16.0a0+cxx11.abi [conda] N/A